© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4444
    Prev
    Next
    INDEX
    Explanations

    license and redistribution terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¶ĬæĿ¥è¶Ĭ好
    -0.09
     Kick
    -0.08
    éģĩéļ¾
    -0.08
    ailer
    -0.08
    å®ŀåľ°
    -0.08
    沿
    -0.08
    æĹ©çĤ¹
    -0.08
    åī¥
    -0.08
     kick
    -0.08
    åİ®
    -0.08
    POSITIVE LOGITS
    åĪĬ
    0.09
    åĨ³ä¸į
    0.08
    åħħæĸ¥
    0.08
    Reuse
    0.08
    .tm
    0.08
    uters
    0.08
    顶端
    0.08
    年级
    0.08
    ullet
    0.08
    _hp
    0.08
    Activations Density 0.424%

    No Known Activations